{"url":"/dataset/kvasir-vqa","name":"Kvasir-VQA","full_name":"A Text-Image Pair GI Tract Dataset","description_markdown":"The Kvasir-VQA dataset is an extended dataset derived from the HyperKvasir and Kvasir-Instrument datasets, augmented with question-and-answer annotations. This dataset is designed to facilitate advanced machine learning tasks in gastrointestinal (GI) diagnostics, including image captioning, Visual Question Answering (VQA) and text-based generation of synthetic medical images.","description_withheld":null,"homepage":"https://datasets.simula.no/kvasir-vqa/","introduced_date":"2024-09-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/kvasir-vqa-a-text-image-pair-gi-tract-dataset","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","first_author":"Sushant Gautam","url":null},"license":{"name":"CC BY-NC","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Medical Diagnosis","url":"/task/medical-diagnosis","datasets_with_task":"/datasets/task/medical-diagnosis"},{"name":"Medical Visual Question Answering","url":"/task/medical-visual-question-answering","datasets_with_task":"/datasets/task/medical-visual-question-answering"},{"name":"Medical Image Generation","url":"/task/medical-image-generation","datasets_with_task":"/datasets/task/medical-image-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Kvasir-VQA"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}